enhance remote validation docs

Author: zsimjee

docs/concepts/remote_validation_inference.ipynb

@@ -19,11 +19,7 @@
     "\n",
     ":::note\n",
     "Remote validation inferencing is only available in Guardrails versions 0.5.0 and above.\n",
-    ":::\n",
-    "\n",
-    "::note\n",
-    "To enable/disable, you can run the cli command `guardrails configure` or modify your `~/.guardrailsrc`. For example, to disable remote inference use: `use_remote_inferencing=false`.\n",
-    ":::"
+    ":::\n"
    ]
   },
   {
@@ -114,6 +110,62 @@
     "    display(accumulated_output)\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Toggling Remote Inferencing\n",
+    "\n",
+    "To enable/disable remote inferencing, you can run the cli command `guardrails configure` or modify your `~/.guardrailsrc`.\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "shellscript"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# To disable\n",
+    "guardrails configure --disable-remote-inferencing\n",
+    "\n",
+    "# To enable\n",
+    "guardrails configure --enable-remote-inferencing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To disable remote inferencing from a specific validator, you can add a `use_local` kwarg to the validator's initializer\n",
+    "\n",
+    ":::note\n",
+    "When runnning locally, you may need to reinstall the validator with the --install-local-models flag.\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from guardrails import Guard, install\n",
+    "try:\n",
+    "    from guardrails.hub import ToxicLanguage\n",
+    "except ImportError:\n",
+    "    install(\"hub://guardrails/toxic_language\", install_local_models=True)\n",
+    "    from guardrails.hub import ToxicLanguage\n",
+    "\n",
+    "# uses validator locally.\n",
+    "guard.use(ToxicLanguage(use_local=True))\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -143,6 +195,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    ":::note\n",
+    "\n",
+    "Contact us to host validators in your own VPC with managed hardware.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "# Learn more\n",
+    "\n",
     "To learn more about hosting your own validators, check out the [Host Remote Validator Models doc](/docs/how_to_guides/hosting_validator_models).\n",
     "\n",
     "To learn more about writing your own validators, check out the [Custom validators doc](/docs/how_to_guides/custom_validator)."

docs/getting_started/guardrails_server.md

@@ -122,20 +122,31 @@ A `guardrails` key is added to the response object, which includes the validatio
 ### Advanced Client Usage
 Advanced client usage is available in Python. You can point a Guard shim to the Guardrails server and use it as a normal Guard object.
 
-To do this, you must first set a `use_server` flag in Guardrails settings.
+```python
+# Client code
+from guardrails import Guard
+
+name_guard = Guard.fetch_guard(name="gibberish_guard")
+
+validation_outcome = name_guard.validate("floofy doopy boopy")
+```
+
+
+#### Guardrails < v0.5.9
+In older versions of Guardrails, you need to set the `use_server` var in settings to True.
 
 ```python
 # Client code
 from guardrails import Guard, settings
 
 settings.use_server = True
-
 name_guard = Guard(name="gibberish_guard")
 
 validation_outcome = name_guard.validate("floofy doopy boopy")
 ```
 
 
+
 ## Learn More
 - [Guardrails Server Concepts](../concepts/deploying)
 - [Guardrails CLI Reference](../cli)

docusaurus/sidebars.js

@@ -41,6 +41,7 @@ const sidebars = {
       label: "Migration Guides",
       collapsed: false,
       items: [
+        "migration_guides/0-6-alpha-migration",
         "migration_guides/0-5-migration",
         "migration_guides/0-4-migration",
         "migration_guides/0-3-migration",